Click to add notes
GOOD MORNING
Sir and my dear Friends
CREATED BY VINAY KUSHWAHA & AMAN SHARMA
TODAY I WANT TO EXPLANE AN IMPORTANT TOPIC
Click to add subtitle
RECOMMENDER SYSTEM : A LITERATURE SURVEY
BEFORE STARTING THE TOPIC WE GIVE PRATICAL EXAMPLE OF RECOMMANDATION SYSTEMS
INTRODUCTION
IN TODAYS WORD LOTS OF DATA IS AVAILABLE
SOME BIG COMPANY USE THIS DATA
FOR USING OUR PROFIT
EXAMPLE
E-COMMERS COMPANYS USE THIS HUG AMOUNT OF DATA FOR USING INCREASE OUR SALES FOR EARNING MORE AMOUNT OF PROFIT WITHOUT DOING MUCH HARDWORK
FLIPKART
THIS COMPANY USE USER DATA FOR INCREASE OUR SALES IN SOME FASTIVAL THIS COMPANY OFFERING SOME EXCLUSIVE OFFER FOR USER
EXAMPLE – BY 1 GET 1 FREE , DISCOUNT OFFERS
HISTORY
THE ORIGINS OF MODERN RECOMMENDER SYSTEMS DATE BACK TO THE EARLY 1990s WHEN THEY WERE MAINLY APPLIED EXPERIMENTALLY TO PERSONAL EMAIL AND INFORMATION FILTERING.
DEFINITION
•AN INFORMATION FILTERING SYSTEM SUPPORTING THE USER IN A GIVEN DECISION MAKING SITUATION BY NARROWING THE SET OF POSSIBLE OPTIONS AND PRIORITIZING ITS ELEMENTS IN A SPECIFIC CONTECTS.
HOW DOES A RECOMMENDATION SYSTEM WORKS ?
RECOMMENDATION SYSTEM PROCESSES DATA THROUGH FOUR PHASES AS FOLLOWS :
•COLLECTION
•STORING
•ANALYZING
•FILTERING
COLLECTION
•DATA COLLECTED
• EXPLICIT (RATINGS AND COMMENTS ON PRODUCTS )
•IMPLICIT (PAGE VIEWS, ORDER HISTORY)
STORING
•The type of data that is used to create recommendations can help you decide the kind of storage you should use. -> DATABASE OR SQL DATABASE
ANALYZING
•THE RECOMMENDER SYSTEM FINDS ITEMS WITH SIMILAR USER ENGAGEMENT DATA AFTER ANALYSIS.
FILTERING
•This is the last step where data gets filtered to access the relevant information required to provide recommendations to the user. To enable this, you will need to choose an algorithm suiting the recommendation system.
TYPES OF RECOMMENDATION SYSTEMS
•Content based (CB)
•Collaborative filtering (CF)
•Hybrid filtering (CB + CF)
CONTENT BASED RECOMMENDER SYSTEM
•CONTENT SIMILARITY OR ITEM SIMILARITY
•TRIES TO GUESS THE FEATURES OR BEHAVIOR OF A USER GIVEN THE ITEM’S FEATURES, HE/SHE REACTS POSITIVELY TO
ADVANTAGE
•Model doesn’t need data of other users since recommendations are specific to a single user.
•It makes it easier to scale to a large number of users.
•The model can Capture the specific Interests of the user and can recommend items that very few other users are interested in.
•
DISADVANTAGE
•Feature representation of items is hand-engineered to some extent, this tech requires a lot of domain knowledge.
•The model can only make recommendations based on the existing interest of a user. In other words, the model has limited ability to expand on the user’s existing interests.
COLLABORATIVE FILTERING RECOMMENDER SYSTEM
•Collaborative does not need the features of the items to be given. Every user and item is described by a feature vector or embedding
• User similarly or same mentality user
SUBTYPE OF COLLABORATIVE FILTERING
•USER BASED COLLABORATIVE FILTERING
•ITEM BASED COLLABORATIVE FILTERING
USER BASED COLLABORATIVE FILTERING
•Rating of the item is done using the rating of neighbouring users. In simple words, it is based on the notion of users’ similarity.
•Let see an example. On the left side, you can see a picture where 3 children named A, B, C, and 4 fruits i.e., grapes, strawberry, watermelon, and orange respectively.
•Based on the image let assume A purchased all 4 fruits, B purchased only strawberry and C purchased strawberry as well as watermelon. Here A & C are similar kinds of users because of this C will be recommended Grapes and Orange as shown in dotted line.
ITEM BASED COLLABORATIVE FILTERING
•The rating of the item is predicted using the user’s own rating on neighbouring items. In simple words, it is based on the notion of item similarity.
•Let us see with an example as talked above about users and items. Here the only difference is that we see similar items, not similar users like if you see grapes and watermelon, you will realize that watermelon is purchased by all of them but grapes are purchased by Children A & B. Hence Children C is being recommended grapes.
•It works well even if the data is small.
•This model helps the users to discover a new interest in a given item but the model might still recommend it because similar users are interested in that item.
•No need for Domain Knowledge
•It cannot handle new items because the model doesn’t get trained on the newly added items in the database. This problem is known as Cold Start Problem.
•Side Feature Doesn’t have much importance. Here Side features can be actor name or releasing year in the context of movie recommendation.
HYBRID RECOMMENDATION SYSTEM
HYBIRD =CF+CB
•CB -> CONTENT BASED RECOMMENDATION SYSTEM
•CF->COLLABORATIVE FILTERING RECOMMENDATION SYSTEM
•In hybrid recommendation systems, products are recommended using both content-based and collaborative filtering simultaneously to suggest a broader range of products to customers. This recommendation system is up-and-coming and is said to provide more accurate recommendations than other recommender systems
Let everyone follow along by enabling live captions and subtitles. Your words will be automatically transcribed, translated, and displayed on the main screen.
Subtitles support 10+ spoken languages and 60+ subtitle languages.
